[1]王凯翔.基于多元回归和神经网络途径的太湖富营养化指标分析与预测[J].南京师范大学学报(工程技术版),2017,17(02):070.[doi:10.3969/j.issn.1672-1292.2017.02.011]
 Wang Kaixiang.Taihu Lake Eutrophication Index Analysis and PredictionBased on Multiple Regression and Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2017,17(02):070.[doi:10.3969/j.issn.1672-1292.2017.02.011]
点击复制

基于多元回归和神经网络途径的太湖富营养化指标分析与预测
分享到:

南京师范大学学报(工程技术版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
17卷
期数:
2017年02期
页码:
070
栏目:
计算机工程
出版日期:
2017-06-30

文章信息/Info

Title:
Taihu Lake Eutrophication Index Analysis and PredictionBased on Multiple Regression and Neural Network
文章编号:
1672-1292(2017)02-0070-05
作者:
王凯翔
南京师范大学计算机科学与技术学院,江苏 南京 210023
Author(s):
Wang Kaixiang
School of Computer Science and Technology,Nanjing Normal University,Nanjing 210023,China
关键词:
富营养化预测相关系数多元线性回归分析BP神经网络
Keywords:
eutrophicationforecastcorrelation coefficientthe multivariate linear regression analysisthe BP neural network
分类号:
TP18
DOI:
10.3969/j.issn.1672-1292.2017.02.011
文献标志码:
A
摘要:
水体富营养化是目前太湖面临的一个重大环境问题,有效地预测湖泊的水质变化对防治富营养化至关重要. 现有的预测方案很多依赖于一些常见的与目标变量相关的因素,针对太湖这一具体对象,难以全面准确地分析相关因素之间的联系以及预见目标变量的变化趋势. 本文首先寻找出太湖富营养化的所有可能的影响因素,提供较为全面的备选变量以期更好地查找出目标变量的相关因素. 选择总氮这一富营养化重要评价指标作为分析和预测的对象,根据各影响因子与总氮之间的相关系数筛选出影响程度较高的因素. 分别运用多元线性回归分析方法和BP神经网路预测方法对总氮的变化进行预测研究,并将两种方法的预测性能进行比较. 结果表明,从较为全面的变量中选出的影响因子可较好地预测总氮的变化情况,多元线性回归和BP神经网络方法的实验结果都较好,从拟合优度和均方误差的角度看,BP神经网络的预测效果更好.
Abstract:
Eutrophication of body of water is a major environmental problem of the Taihu lake,and the eutrophication prediction is an effective early warning method to know the change of lake water quality. Now there are a lot of prediction schemes depending on the existing known factors related to the target,and it is difficult to fully accurate analysis of the relationship between the related factors and predict the change trend of target variable. In this paper,firstly,we find out all of the possible affecting factors of the eutrophication of Taihu lake,then we can obtain a better target variable of related factors with a more comprehensive variables provided. We select the eutrophication of total nitrogen as the object of analysis and forecasting. The factors are selected by their correlation with total nitrogen. We conduct the prediction study for the change of total nitrogen with multiple linear regression analysis method and BP neural network prediction method,and compare the performances of the two methods. The results show that the variables selected can well predict the changes of total nitrogen. The experimental results obtained from multiple linear regression and BP neural network method are both accurate,from the perspectives of the goodness of fit and the mean square error,and the BP neural network is better.

参考文献/References:

[1] 陈小锋,揣小明,杨柳燕. 中国典型湖区湖泊富营养化现状、历史演变趋势及成因分析[J]. 生态与农村环境学报,2014,30(4):438-443.
CHEN X F,CHUAI X M,YANG L Y.Status quo,historical evolution and causes of eutrophication in lakes in typical lake regions of China[J]. Journal of ecology and rural environment,2014,30(4):438-443.(in Chinese)
[2]钱奎梅,陈宇炜,宋晓兰. 太湖浮游植物优势种长期演化与富营养化进程的关系[J]. 生态科学,2008,27(2):65-70.
QIAN K M,CHEN Y W,SONG X L. Long-term development of phytoplankton dominant species related to eutrophicarion in Lake Taihu[J]. Ecological science,2008,27(2):65-70.(in Chinese)
[3]崔嘉宇,郁建桥,吕学研,等. 太湖富营养化指标BP人工神经网络预测模型的建立[J]. 环境研究与监测,2014,27(3):50-54.
CUI J Y,YU J Q,Lü X Y. Establishment of BP artificial neural network prediction model for eutrophication index of Lake Taihu[J]. Environmental study and monitoring,2014,27(3):50-54.(in Chinese)
[4]韩菲,陈永灿,刘昭伟. 湖泊及水库富营养化模型研究综述[J]. 水科学进展,2003,14(6):786-790.
HAN F,CHEN Y C,LIU Z W. Advance in the eutrophication models for lakes and reservoirs[J]. Advances in water science,2003,14(6):786-790.(in Chinese)
[5]胡小贞,耿荣妹,许秋瑾,等. 太湖流域流经不同类型缓冲带入湖河流秋、冬季氮污染特征[J]. 湖泊科学,2016,28(6):1 194-1 203.
HU X Z,GENG R M,XU Q J,et al. Charactistics of nitrogen pollution of rivers flowing through different lake buffer strips in autumn/winter,Taihu Basin[J]. Journal of lake sciences,2016,28(6):1 194-1 203.(in Chinese)
[6]吴雅丽,许海,杨桂军,等. 太湖水体氮素污染状况研究进展[J]. 湖泊科学,2014,26(1):19-28.
WU Y L,XU H,YANG G J.Progress in nitrogen pollution research in Lake Taihu[J]. Journal of lake sciences,2014,26(1):19-28.(in Chinese)
[7]何晓群. 多元统计分析[M]. 北京:中国人民大学出版社,2011.
HE X Q. Multivariate statistical analysis[M]. Beijing:China Renmin University Press,2011.(in Chinese)
[8]何晓群,刘文卿. 应用回归分析[M]. 北京:中国人民大学出版社,2015:57-90.
HE X Q,LIU W Q. Application regression analysis[M]. Beijing:China Renmin University Press,2015:57-90.(in Chinese)
[9]丛爽. 面向MATLAB工具箱的神经网络理论与应用[M]. 合肥:中国科学技术大学出版社,2009.
CONG S. Neural network theory and application with MATLAB toolboxes[M]. Hefei:Press of University of Science and Technology of China,2009.(in Chinese)
[10]李祚泳,汪嘉杨,金相灿,等. 基于进化算法的湖泊富营养化投影寻踪回归预测模型[J]. 四川大学学报(工程技术版),2007,39(2):1-8.
LI Z Y,WANG J Y,JIN X C,et al. Evolution algorithm based forecasting model for lake eutrophication using PPR[J]. Journal of Sichuan university(engineering and technology edition),2007,39(2):1-8.(in Chinese)
[11]崔东文. BP神经网络模型在湖泊富营养化程度评价中的应用[J]. 云南水利水电,2011(1):61-67.
CUI D W.Appliance of BP neural network model in evaluation of lake eutrophication degree[J]. Journal of water conservancy and hydropower in Yunnan,2011(1):61-67.(in Chinese)

相似文献/References:

[1]程红林.动态模糊逻辑在智能交通控制系统中的应用研究[J].南京师范大学学报(工程技术版),2015,15(03):045.
 Cheng Honglin.Research on Application of Dynamic Fuzzy Logic in IntelligentTransportation Control System[J].Journal of Nanjing Normal University(Engineering and Technology),2015,15(02):045.

备注/Memo

备注/Memo:
收稿日期:2016-11-09.
基金项目:2014年国家级大学生创新训练项目(201410319038Z).
通讯联系人:王凯翔,硕士研究生,研究方向:数据库与数据挖掘. E-mail:15651805876@163.com
更新日期/Last Update: 2017-06-30